© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91602
    Prev
    Next
    INDEX
    Explanations

    mental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     divisible
    -0.09
     Ethernet
    -0.08
     divine
    -0.08
     tedious
    -0.08
    ected
    -0.07
     эпох
    -0.07
    粒
    -0.07
     spacecraft
    -0.07
     electromagnetic
    -0.07
     поряд
    -0.07
    POSITIVE LOGITS
     PTSD
    0.14
     psicológico
    0.14
    心理
    0.14
     psychological
    0.13
     психолог
    0.13
     antidepress
    0.12
     wellness
    0.12
     mentale
    0.12
     anxiety
    0.12
     Anxiety
    0.12
    Activations Density 0.128%

    No Known Activations